Multiple recursive projection twin support vector machine for multi-class classification

  • Chun-Na Li
  • Yun-Feng Huang
  • He-Ji Wu
  • Yuan-Hai Shao
  • Zhi-Min Yang
Original Article

DOI: 10.1007/s13042-014-0289-2

Cite this article as:
Li, CN., Huang, YF., Wu, HJ. et al. Int. J. Mach. Learn. & Cyber. (2016) 7: 729. doi:10.1007/s13042-014-0289-2

Abstract

For multi-class classification problem, a novel multiple projection twin support vector machine (Multi-PTSVM) is proposed. Our Multi-PTSVM solves \(K\) quadratic programming problems (QPPs) to obtain \(K\) projection axes, which is similar to binary PTSVM, but the regularization terms and recursive procedure are introduced for each class, which improve the generalization ability greatly. Comparisons against the Multi-SVM, Multi-TWSVM, Multi-GEPSVM, and our Multi-PTSVM on both synthetic and benchmark datasets indicate that our Multi-PTSVM has its advantages.

Keywords

Multi-class classification Multiple recursive projection Twin support vector machine Projection twin support vector machine 

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Chun-Na Li
    • 1
  • Yun-Feng Huang
    • 2
  • He-Ji Wu
    • 3
  • Yuan-Hai Shao
    • 1
  • Zhi-Min Yang
    • 1
  1. 1.Zhijiang CollegeZhejiang University of TechnologyHangzhouPeople’s Republic of China
  2. 2.Hangzhou Navigation Instrument Company Limited and Institute of special equipmentZhejiang University of TechnologyHangzhouPeople’s Republic of China
  3. 3.College of ScienceZhejiang University of TechnologyHangzhouPeople’s Republic of China

Personalised recommendations